# DeepMultiConnectome: Deep Multi-Task Prediction of Structural Connectomes Directly from Diffusion MRI Tractography

arXiv: https://arxiv.org/abs/2505.22685 · HTML: https://mlsanity.com/paper/2505.22685/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 62 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 16 of 16)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [TractSeg - Fast and accurate white matter tract segmentation](https://mlsanity.com/paper/1805.07103/) (2018)
- [Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions](https://mlsanity.com/paper/2207.08975/) (2022)
- [Tractogram filtering of anatomically non-plausible fibers with geometric deep learning](https://mlsanity.com/paper/2003.11013/) (2020)
- [Model and predict age and sex in healthy subjects using brain white matter features: A deep learning approach](https://mlsanity.com/paper/2202.03595/) (2022)
- [Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation](https://mlsanity.com/paper/2205.00627/) (2022)
- [TractCloud: Registration-free tractography parcellation with a novel local-global streamline point cloud representation](https://mlsanity.com/paper/2307.09000/) (2023)
- [White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical Region Localization via Geometric Deep Learning](https://mlsanity.com/paper/2207.02402/) (2022)
- [TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography](https://mlsanity.com/paper/2301.01911/) (2023)
- [DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks](https://mlsanity.com/paper/1906.03051/) (2019)
- [Fiber Tract Shape Measures Inform Prediction of Non-Imaging Phenotypes](https://mlsanity.com/paper/2303.09124/) (2023)
- [The shape of the brain's connections is predictive of cognitive performance: an explainable machine learning study](https://mlsanity.com/paper/2410.15108/) (2024)
- [Detailed delineation of the fetal brain in diffusion MRI via multi-task learning](https://mlsanity.com/paper/2409.06716/) (2024)
- [TractShapeNet: Efficient Multi-Shape Learning with 3D Tractography Point Clouds](https://mlsanity.com/paper/2410.22099/) (2024)

## Abstract (arXiv)

Diffusion MRI (dMRI) tractography enables in vivo mapping of brain structural connections, but traditional connectome generation is time-consuming and requires gray matter parcellation, posing challenges for large-scale studies. We introduce DeepMultiConnectome, a deep-learning model that predicts structural connectomes directly from tractography, bypassing the need for gray matter parcellation while supporting multiple parcellation schemes. Using a point-cloud-based neural network with multi-task learning, the model classifies streamlines according to their connected regions across two parcellation schemes, sharing a learned representation. We train and validate DeepMultiConnectome on tractography from the Human Connectome Project Young Adult dataset (n = 1000), labeled with an 84 and 164 region gray matter parcellation scheme. DeepMultiConnectome predicts multiple structural connectomes from a whole-brain tractogram containing 3 million streamlines in approximately 40 seconds. DeepMultiConnectome is evaluated by comparing predicted connectomes with traditional connectomes generated using the conventional method of labeling streamlines using a gray matter parcellation. The predicted connectomes are highly correlated with traditionally generated connectomes (r = 0.992 for an 84-region scheme; r = 0.986 for a 164-region scheme) and largely preserve network properties. A test-retest analysis of DeepMultiConnectome demonstrates reproducibility comparable to traditionally generated connectomes. The predicted connectomes perform similarly to traditionally generated connectomes in predicting age and cognitive function. Overall, DeepMultiConnectome provides a scalable, fast model for generating subject-specific connectomes across multiple parcellation schemes.